Diffusion-based Neural Network Weights Generation

arXiv:2402.18153v1 Announce Type: new
Abstract: Transfer learning is a topic of significant interest in recent deep learning research because it enables faster convergence and improved performance on new tasks. While the performance of transfer learning depends on the similarity of the source data to the target data, it is costly to train a model on a large number of datasets. Therefore, pretrained models are generally blindly selected with the hope that they will achieve good performance on the given task. …

abstract arxiv convergence cs.ai cs.lg data deep learning diffusion faster network neural network performance research source data tasks train transfer transfer learning type